Spatial autocorrelation in masting phenomena of Quercus serrata detected by multi-spectral imaging

Abstract

We developed a multiple linear regression methodology for estimating acorn yield of Quercus serrata from airborne multi-spectral images. Using the models developed, we estimated the spatial distribution of acorn yields on the aerial images. We also calculated spatial autocorrelation from the estimated spatial distribution of yields, and evaluated the spatial pattern by comparison with the simulation output from Satake and Iwasa's [Satake, A., Iwasa, Y., 2002a. Spatially limited pollen exchange and a long-range synchronization of trees. Ecology 83, 993–1005] theoretical models, which assume internal allocation and pollen exchange between trees within a finite range. A significant correlation was found between logarithmic acorn yield and the multi-spectral data observed on June 6, 2003 ( R 2 = 0.37, p < 0.05) and on May 26, 2004 ( R 2 = 0.44, p < 0.01); these relationships were also confirmed by leave-one-out cross-validation ( p < 0.05). Through an image segmentation procedure, approximately 5700 canopies were identified. The acorn yields of these canopies were estimated by applying the model developed. The correlation coefficients calculated from the estimated spatial distributions of yield decreased as distance increased. Our experimentally estimated spatial distribution agrees with the patterns of the correlograms of spatial pattern derived from Sakate and Iwasa's models. Combinations of our findings and their simulation results suggest that an endogenous mechanism may drive the masting of Q. serrata.